| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135 |
- Global:
- debug: false
- use_gpu: true
- epoch_num: 75
- log_smooth_window: 20
- print_batch_step: 10
- save_model_dir: ./output/PP-OCRv5_server_rec
- save_epoch_step: 1
- eval_batch_step: [0, 2000]
- cal_metric_during_train: true
- calc_epoch_interval: 1
- pretrained_model:
- checkpoints:
- save_inference_dir:
- use_visualdl: false
- infer_img: doc/imgs_words/ch/word_1.jpg
- character_dict_path: ./ppocr/utils/dict/ppocrv5_dict.txt
- max_text_length: &max_text_length 25
- infer_mode: false
- use_space_char: true
- distributed: true
- save_res_path: ./output/rec/predicts_ppocrv5.txt
- d2s_train_image_shape: [3, 48, 320]
- Optimizer:
- name: Adam
- beta1: 0.9
- beta2: 0.999
- lr:
- name: Cosine
- learning_rate: 0.0005
- warmup_epoch: 1
- regularizer:
- name: L2
- factor: 3.0e-05
- Architecture:
- model_type: rec
- algorithm: SVTR_HGNet
- Transform:
- Backbone:
- name: PPHGNetV2_B4
- text_rec: True
- Head:
- name: MultiHead
- head_list:
- - CTCHead:
- Neck:
- name: svtr
- dims: 120
- depth: 2
- hidden_dims: 120
- kernel_size: [1, 3]
- use_guide: True
- Head:
- fc_decay: 0.00001
- - NRTRHead:
- nrtr_dim: 384
- max_text_length: *max_text_length
- Loss:
- name: MultiLoss
- loss_config_list:
- - CTCLoss:
- - NRTRLoss:
- PostProcess:
- name: CTCLabelDecode
- Metric:
- name: RecMetric
- main_indicator: acc
- Train:
- dataset:
- name: MultiScaleDataSet
- ds_width: false
- data_dir: ./train_data/
- ext_op_transform_idx: 1
- label_file_list:
- - ./train_data/train_list.txt
- transforms:
- - DecodeImage:
- img_mode: BGR
- channel_first: false
- - RecAug:
- - MultiLabelEncode:
- gtc_encode: NRTRLabelEncode
- - KeepKeys:
- keep_keys:
- - image
- - label_ctc
- - label_gtc
- - length
- - valid_ratio
- sampler:
- name: MultiScaleSampler
- scales: [[320, 32], [320, 48], [320, 64]]
- first_bs: &bs 64
- fix_bs: false
- divided_factor: [8, 16] # w, h
- is_training: True
- loader:
- shuffle: true
- batch_size_per_card: *bs
- drop_last: true
- num_workers: 16
- Eval:
- dataset:
- name: SimpleDataSet
- data_dir: ./train_data
- label_file_list:
- - ./train_data/val_list.txt
- transforms:
- - DecodeImage:
- img_mode: BGR
- channel_first: false
- - MultiLabelEncode:
- gtc_encode: NRTRLabelEncode
- - RecResizeImg:
- image_shape: [3, 48, 320]
- - KeepKeys:
- keep_keys:
- - image
- - label_ctc
- - label_gtc
- - length
- - valid_ratio
- loader:
- shuffle: false
- drop_last: false
- batch_size_per_card: 128
- num_workers: 4
|
